Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit History
Automated Leaderboard Update
bea903d
orionw
commited on
working
f11b057
Create test.txt
5250137
unverified
Orion Weller
commited on
Create main.yml
16c6ae8
unverified
Orion Weller
commited on
Update model_meta.yaml
468feee
verified
Skip some GGUF/duplicate models
9e4c672
verified
Skip GGUF model
0b972e2
verified
Skip GGUF model
577cb80
verified
Skip GGUF model
7b34a73
verified
Raise error via log
9eaef28
Fix metric names & metadata new format
6181979
Fix seq len
3be8255
Multiple LEMB metrics & fix legacy french naming
767d579
fix metrics for LongEmbed (#124)
f8ed0b8
verified
Hotfix
70c518e
Update clustering emoji to ☘️
536679f
verified
Make search case insensitive
a812c3b
Tom Aarsen
commited on
update: elser-v2 metadata (#119)
ee1fec4
verified
Skip dups
1c27eec
verified
Add LongEmbed leaderboard
ca3620e
Remove dup
86187d3
verified
Remove dup
e7bd51e
verified
Remove dup
d22f232
verified
Skip unusable model
f4a5a9a
verified
Skip bge dup
0125eeb
verified
Add elser-v2
ac6b09a
Skip duplicate
18791f2
verified
No longer skip NV-Embed-v1
c88beb4
verified
Skip the nvidia/NV-Embed-v1 model until the CQADupstackRetrieval metrics are corrected
3b5dc67
verified
Skip a GGUF-ified model
2609efb
verified
Add more models to skip
5a511bc
Tom Aarsen
commited on
Skip an e5 copy (the MTEB results are identical/not updated)
b23bfc1
verified
remove_description_overall (#111)
01976f0
verified
add_followir_tab (#102)
f1fa713
verified
add meta data for gte-Qwen1.5-7B-instruct: (#110)
83fe3f0
verified
Upload EXTERNAL_MODEL_RESULTS.json
44ed3a2
verified
Remove duplicate LLM2Vec-Llama-2 results (#108)
c40a549
verified
Upload EXTERNAL_MODEL_RESULTS.json
32394da
verified
LLM2Vec Llama-3 metadata (#104)
cce7a50
verified
Upload EXTERNAL_MODEL_RESULTS.json
611acdc
verified
Refactor code: Pull leaderboards and models configurations out of the app.py (#106)
7aae94f
verified
Update app.py
911be8d
verified
Add voyage
807cc67
verified
Add dwzhu/e5-base-4k as a pytorch_model.bin model with fp16
abf58d4
Tom Aarsen
commited on